Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 167 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.7468. Min Range: -1.7468

Max Act: 1.7468. Min Act: -0.0001

Data Index: 68094 (C4 (Web Text))

Max Activating Token Index: 81

Text #1

Max Range: 1.7468. Min Range: -1.7468

Max Act: 1.5488. Min Act: -0.0001

Data Index: 1068358 (C4 (Web Text))

Max Activating Token Index: 383

Text #2

Max Range: 1.7468. Min Range: -1.7468

Max Act: 1.6691. Min Act: -0.0001

Data Index: 546679 (C4 (Web Text))

Max Activating Token Index: 515

Text #3

Max Range: 1.7468. Min Range: -1.7468

Max Act: 1.4005. Min Act: -0.0001

Data Index: 1143340 (C4 (Web Text))

Max Activating Token Index: 404

Text #4

Max Range: 1.7468. Min Range: -1.7468

Max Act: 1.3437. Min Act: -0.0001

Data Index: 523046 (C4 (Web Text))

Max Activating Token Index: 509

Text #5

Max Range: 1.7468. Min Range: -1.7468

Max Act: 1.3948. Min Act: -0.0001

Data Index: 393970 (C4 (Web Text))

Max Activating Token Index: 73

Text #6

Max Range: 1.7468. Min Range: -1.7468

Max Act: 1.3869. Min Act: -0.0001

Data Index: 271432 (C4 (Web Text))

Max Activating Token Index: 163

Text #7

Max Range: 1.7468. Min Range: -1.7468

Max Act: 1.3867. Min Act: -0.0001

Data Index: 1215767 (C4 (Web Text))

Max Activating Token Index: 478

Text #8

Max Range: 1.7468. Min Range: -1.7468

Max Act: 1.3265. Min Act: -0.0001

Data Index: 917711 (C4 (Web Text))

Max Activating Token Index: 307

Text #9

Max Range: 1.7468. Min Range: -1.7468

Max Act: 1.3262. Min Act: -0.0001

Data Index: 699908 (C4 (Web Text))

Max Activating Token Index: 118

Text #10

Max Range: 1.7468. Min Range: -1.7468

Max Act: 1.3213. Min Act: -0.0001

Data Index: 293221 (C4 (Web Text))

Max Activating Token Index: 94

Text #11

Max Range: 1.7468. Min Range: -1.7468

Max Act: 1.2494. Min Act: -0.0001

Data Index: 291382 (C4 (Web Text))

Max Activating Token Index: 155

Text #12

Max Range: 1.7468. Min Range: -1.7468

Max Act: 1.2875. Min Act: -0.0001

Data Index: 36139 (C4 (Web Text))

Max Activating Token Index: 204

Text #13

Max Range: 1.7468. Min Range: -1.7468

Max Act: 1.2696. Min Act: -0.0001

Data Index: 364013 (C4 (Web Text))

Max Activating Token Index: 228

Text #14

Max Range: 1.7468. Min Range: -1.7468

Max Act: 1.2979. Min Act: -0.0001

Data Index: 834203 (C4 (Web Text))

Max Activating Token Index: 71

Text #15

Max Range: 1.7468. Min Range: -1.7468

Max Act: 1.2134. Min Act: -0.0001

Data Index: 1118120 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 1.7468. Min Range: -1.7468

Max Act: 1.2984. Min Act: -0.0001

Data Index: 1045294 (C4 (Web Text))

Max Activating Token Index: 317

Text #17

Max Range: 1.7468. Min Range: -1.7468

Max Act: 1.5651. Min Act: -0.0001

Data Index: 808372 (C4 (Web Text))

Max Activating Token Index: 365

Text #18

Max Range: 1.7468. Min Range: -1.7468

Max Act: 1.2330. Min Act: -0.0001

Data Index: 1272084 (C4 (Web Text))

Max Activating Token Index: 37

Text #19

Max Range: 1.7468. Min Range: -1.7468

Max Act: 1.2946. Min Act: -0.0001

Data Index: 844846 (C4 (Web Text))

Max Activating Token Index: 65